qwen3-max
Qwen3 Max is a chat model developed by Qwen, capable of handling a wide range of tasks including function calling, JSON mode, reasoning, streaming, and text generation. It is genuinely best at tasks that require generating human-like text and code, as evidenced by its top 25% scores on the MMLU-Pro and LiveCodeBench benchmarks.
Input
Output
Context
256K
Max Output
66K
Parameters
-
Technical Specifications
Model TypeChat
Context Window256,000 tokens
Max Output Tokens65,536 tokens
ParametersNot available
Release DateSep 23, 2025
Training CutoffJun 1, 2025
Licenseproprietary
Open SourceNo
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
11.1%
HLE
46.7%
AA-LCR
76.4%
GPQA
74.3%
Tau2-Bench
80.7%
AIME 2025
44.1%
IFBench
38.3%
SciCode
84.1%
MMLU Pro
80.7
Math
76.7%
LiveCodeBench
24.0
Intelligence
20.5%
Terminal-Bench Hard
Resources & Links
proprietary, Proprietary - API access only
More Models by Qwen
qwen3-235b-a22b-thinking-2507262K context · 235B · Open weightsQwen 3 4B Thinking 2507262K context · 4B · Open weightsQwen 2.5 32B Instruct33K context · 32.8B · Open weightsQwen 2.5 14B Instruct AWQ33K context · 14.8B · Open weightsQwen 3 VL 8B Instruct262K context · 8.8B · Open weightsQwen 3.5 9B262K context · 9.7B · Open weights
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Aug 6, 2026
Your AI stack shouldn't stand still.
Every month new models become cheaper, faster, and more capable. Inferbase ensures your application automatically benefits without changing a single API call.